paper-with-me

홈 › Papers

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Adversarial Robustness

2021-06-18 · ICML Workshop AML 2021 7 · Jongheon Jeong, Sejun Park, Minkyu Kim, Heung-Chang Lee, DoGuk Kim, Jinwoo Shin

Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\ell_2$-adversarial perturbations. Under the paradigm, the robustness of a classifier is aligned with the prediction confidence, i.e., the higher confidence from a smoothed classifier implies the better robustness. This motivates us to rethink the fundamental trade-off between accuracy and robustness in terms of calibrating confidences of smoothed classifier. In this paper, we propose a simple training scheme, coined SmoothMix, to control the robustness of smoothed classifiers via self-mixup: it trains convex combinations of samples along the direction of adversarial perturbation for each input. The proposed procedure effectively identifies over-confident, near off-class samples as a cause of limited robustness in case of smoothed classifiers, and offers an intuitive way to adaptively set a new decision boundary between these samples for better robustness. Our experiments show that the proposed method can significantly improve the certified $\ell_2$-robustness of smoothed classifiers compared to state-of-the-art robust training methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness

2021-11-17 · NeurIPS 2021 12 · Jongheon Jeong, Sejun Park, Minkyu Kim, Heung-Chang Lee 외

Randomized smoothing is currently a state-of-the-art method to construct a certifiably robust classifier from neural networks against $\ell_2$-adversarial perturbations. Under the paradigm, the robustness of a classifier…

Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation

2023-07-10 · Zhexin Zhang, Jiaxin Wen, Minlie Huang

Large pre-trained language models achieve impressive results across many tasks. However, recent works point out that pre-trained language models may memorize a considerable fraction of their training data, leading to the…

Memorization

SmoothMix: A Simple Yet Effective Data Augmentation to Train Robust Classifiers

2020-06-01 · Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2020 6 · Jin-ha Lee, Muhammad Zaigham Zaheer, Marcella Astrid, Seung-Ik Lee

Data augmentation has been proven effective which, by preventing overfitting, can not only enhances the performance of a deep neural network but also leads to a better generalization even with limited dataset. Recently i…

Data Augmentationimage-classificationImage Classification

Confidence-aware Training of Smoothed Classifiers for Certified Robustness

2022-12-18 · Jongheon Jeong, Seojin Kim, Jinwoo Shin

Any classifier can be "smoothed out" under Gaussian noise to build a new classifier that is provably robust to $\ell_2$-adversarial perturbations, viz., by averaging its predictions over the noise via randomized smoothin…

Adversarial Robustness

Improving Calibration by Relating Focal Loss, Temperature Scaling, and Properness

2024-08-21 · Viacheslav Komisarenko, Meelis Kull

Proper losses such as cross-entropy incentivize classifiers to produce class probabilities that are well-calibrated on the training data. Due to the generalization gap, these classifiers tend to become overconfident on t…

image-classificationImage Classification